TREC DL 20

The 'TREC DL 20' dataset is a benchmark used to evaluate document ranking systems, specifically focusing on deep semantic inference and reasoning-intensive retrieval tasks.

Papers using TREC DL 20 (6)

RankEvolve: Automating the Discovery of Retrieval Algorithms via LLM-Driven Evolution2026BracketRank: Large Language Model Document Ranking via Reasoning-based Competitive Elimination2026SumRank: Aligning Summarization Models for Long-Document Listwise Reranking2026RankSteer: Activation Steering for Pointwise LLM Ranking2026How Good are LLM-based Rerankers? An Empirical Analysis of State-of-the-Art Reranking Models2025DeAR: Dual-Stage Document Reranking with Reasoning Agents via LLM Distillation2025